#!/usr/bin/perl

use Bio::SeqIO;
use Bio::SeqUtils;

#=================================
#Script to trim trailing Xs leftover from incomplete codons
#at the end of a DNA sequence.
#NB:  Will only translate in 1st frame and only trim X's from end
#briandotoakleyatarsdotusdadotgov
#k.purdy at warwick.ac dot uk
#=================================

#---define input file----
$usage = "\n\nUsage:  $0 filename\n\n";
my $input_file = $ARGV[0] or die $usage;
		
my $seqin = Bio::SeqIO->new(-file => $input_file, -format => 'fasta' );
$output_file='seqs_trimmed_of_Xs.fas';
$out = Bio::SeqIO->new(-file => ">$output_file", -format => 'fasta');

print "\nScript is running...\n";


while (my $seqobj = $seqin->next_seq())  {
	$nuc_length = $seqobj->length;
	$full_codon_nuc_length = $nuc_length/3;
		if ($full_codon_nuc_length =~ /\d+\.33/) {
		$chop=1;
		}
		elsif ($full_codon_nuc_length =~ /\d+\.66/) {
		$chop=2;
		}
		elsif ($full_codon_nuc_length =~ /\d+/) {
		$chop=0;
		}
	
	print "\n",$seqobj->id,"  Trimming $chop";
	$trunc_seqobj=$seqobj->trunc(1,($nuc_length-$chop));
	$out->write_seq($trunc_seqobj);
}



print "\n\nTrimmed sequences written to:  ", $output_file,"\n";